AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference

ArXi:2505.13531v2 Announce Type: replace-cross Assessing Large Language Models'(LLMs) underlying value differences enables comprehensive comparison of their misalignment, cultural adaptability, and biases. Nevertheless, current value measurement methods face the informativeness challenge: with often outdated, contaminated, or generic test questions, they can only capture the orientations on comment safety values, e.g., HHH, shared among different LLMs, leading to indistinguishable and uninformative results. To address this problem, we